© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12864
    Prev
    Next
    INDEX
    Explanations

    actions and control decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quiere
    -1.04
     recognizing
    -1.00
    hanced
    -0.94
     kombat
    -0.92
     teis
    -0.91
    ídos
    -0.91
     氏
    -0.89
     pandemi
    -0.89
     vokal
    -0.88
     ચ
    -0.88
    POSITIVE LOGITS
     decisions
    1.73
     choices
    1.66
     decision
    1.41
     output
    1.32
     action
    1.31
     actions
    1.29
     choice
    1.26
    决策
    1.22
     control
    1.22
     input
    1.19
    Activations Density 0.016%

    No Known Activations